Product we built · On-device AISakinah Audio: real-time AI that removes instruments from video sound, on the device
A small audio model and one engine that run inside the browser, the phone and the desktop. Speech and everyday sounds stay, musical instruments go, and no audio ever leaves the device.
Visit sakinahaudio.com
- Type
- Our own product, built end to end
- Platforms
- Chrome, Firefox, Android, Windows, iPhone, iPad, Mac
- Privacy
- Processing on the device. Nothing recorded or sent
The problem
People who avoid music in everyday content had two bad options: mute the video and lose the speech, or skip the content. Existing separation tools run in the cloud, need an upload and work on files, not on a live video playing in a browser tab or an app.
What we built
A small real-time audio model
Trained to keep speech and everyday sounds and drop instruments, with two modes: remove music, or voice only. It is small enough to ship inside a browser extension and fast enough for live playback.
One engine, every platform
A single Rust engine processes audio in 10 ms blocks. The same engine runs as WebAssembly in the browser, as a native library on Android, iOS and Mac, and as a library in the Windows and Linux apps. Each app is a thin shell around it.
Platform audio capture
Each platform needed its own way in: Web Audio and tab capture in the browser, system audio capture on Android, per-app loopback on Windows, and a Safari extension plus an in-app player on iOS.
Model protection
The model ships encrypted and only opens under the right store identity, so a copied package does not run. Each release carries its own watermark.
Website and store presence
A bilingual Arabic and English website with structured data and search-focused pages, plus store listings, screenshots and a demo video for Chrome, Firefox and Google Play.
The hard parts
Real time on budget phones
On a budget Android phone the engine processes 10 ms of audio in about 5.6 ms. That margin is what keeps the sound from stuttering while a video plays.
No doubled sound
Some Android phones cannot silence the original stream. On those, the app plays the original instead of risking two copies of the audio at once.
Privacy as a design constraint
Nothing is recorded or uploaded, there are no ads and no tracking, and the core feature needs no account. Recording the cleaned audio is blocked wherever the platform allows it.
By the numbers
7
platforms built from one engine
10 ms
audio block, processed in about 5.6 ms on a budget phone
0
bytes of audio leaving the device
Measured on our own test devices. User numbers will be added once the stores approve the apps.
Where it stands
Website live. Chrome and Firefox extensions in store review. Android in a Google Play closed test. Windows, iPhone, iPad and Mac built and waiting on store accounts.
What this means for your project
On-device and edge AI
When data cannot leave the device, or the cloud round trip is too slow, we ship the model to the device and make it fast enough to run there.
Talk about on-device AIReal-time audio and voice
The same discipline of latency budgets, streaming audio and platform capture is what our voice AI work runs on.
See voice AICross-platform product builds
One core, thin shells, store releases on every platform: the way we build AI products that have to ship, not demo.
See AI product buildsNeed AI that runs where the data is?
A 30-minute call about your product and its constraints. Written plan and fixed price within 3 days.
Book a call
